218 -- 6 months later

Continuation of what I loved about the first model, with updated ingredients and method of merging, that is Bayesian merging with manual scoring with samples generated with my LoRA.

In addition, I added one of Aha's models into the mix, specifically cV, because I really enjoyed the Counterfeit aesthetics.

And so, this is what I got. I have been using it as my main 1.5 model. The reason it's a separate upload is because they look different to an extent, it isn't a strict update. I still use both.

No metadata because of 4 letter forbidden word so please add some images if you get something nice.

Amedira rules should apply here, so you can make use of "sle" and "mksks style" in the prompt, although I never rigorously tested whether or not they function properly.

HF page with more info

Check out my sdxl merge if you can run it, it's way more capable than 1.5 models.